Sandbox vectors

Let’s define some vectors which can be used for demonstrations:

manyNumbers <- sample( 1:1000, 20 )
manyNumbers
 [1] 692  76 751 633 474 625 532 756 840 528  80 277 496 534 860 502 842 507 196 531
manyNumbersWithNA <- sample( c( NA, NA, NA, manyNumbers ) )
manyNumbersWithNA
 [1] 840  80  NA 756 277 502 507  76 534 860 842 196 625 751 532  NA 528 633 531 496 692 474  NA
duplicatedNumbers <- sample( 1:5, 10, replace = TRUE )
duplicatedNumbers
 [1] 1 3 3 4 2 4 3 4 4 3
letters
 [1] "a" "b" "c" "d" "e" "f" "g" "h" "i" "j" "k" "l" "m" "n" "o" "p" "q" "r" "s" "t" "u" "v" "w" "x" "y" "z"
LETTERS
 [1] "A" "B" "C" "D" "E" "F" "G" "H" "I" "J" "K" "L" "M" "N" "O" "P" "Q" "R" "S" "T" "U" "V" "W" "X" "Y" "Z"
mixedLetters <- c( sample( letters, 5 ), sample( LETTERS, 5 ) )
mixedLetters
 [1] "k" "e" "n" "a" "s" "Y" "T" "J" "Z" "H"

Are all/any elements TRUE

all( manyNumbers <= 1000 )
[1] TRUE
all( manyNumbers <= 500 )
[1] FALSE
any( manyNumbers > 1000 )
[1] FALSE
any( manyNumbers > 500 )
[1] TRUE
all( !is.na( manyNumbers ) )
[1] TRUE
any( is.na( manyNumbers ) )
[1] FALSE

Which elements are TRUE

Input: logical vector Output: vector of numbers (positions)

which( manyNumbers > 900 )
integer(0)
which( manyNumbersWithNA > 900 )
integer(0)
which( is.na( manyNumbersWithNA ) )
[1]  3 16 23

Filtering vector elements

manyNumbers[ manyNumbers > 900 ] # indexing by logical vector
integer(0)
manyNumbers[ which( manyNumbers > 900 ) ] # indexing by positions
integer(0)
somePositions <- which( manyNumbers > 900 )
manyNumbers[ somePositions ]
integer(0)

Are some elements among other elements

"A" %in% LETTERS
[1] TRUE
c( "X", "Y", "Z" ) %in% LETTERS
[1] TRUE TRUE TRUE
all( c( "X", "Y", "Z" ) %in% LETTERS )
[1] TRUE
all( mixedLetters %in% LETTERS )
[1] FALSE
any( mixedLetters %in% LETTERS )
[1] TRUE
mixedLetters[ mixedLetters %in% LETTERS ]
[1] "Y" "T" "J" "Z" "H"
mixedLetters[ !( mixedLetters %in% LETTERS ) ]
[1] "k" "e" "n" "a" "s"
manyNumbers %in% 300:600
 [1] FALSE FALSE FALSE FALSE  TRUE FALSE  TRUE FALSE FALSE  TRUE FALSE FALSE  TRUE  TRUE FALSE  TRUE FALSE  TRUE
[19] FALSE  TRUE
which( manyNumbers %in% 300:600 )
[1]  5  7 10 13 14 16 18 20
sum( manyNumbers %in% 300:600 )
[1] 8

Pick one of two (three) depending on condition

if_else( manyNumbersWithNA >= 500, "large", "small" )
 [1] "large" "small" NA      "large" "small" "large" "large" "small" "large" "large" "large" "small" "large" "large"
[15] "large" NA      "large" "large" "large" "small" "large" "small" NA     
if_else( manyNumbersWithNA >= 500, "large", "small", "UNKNOWN" )
 [1] "large"   "small"   "UNKNOWN" "large"   "small"   "large"   "large"   "small"   "large"   "large"   "large"  
[12] "small"   "large"   "large"   "large"   "UNKNOWN" "large"   "large"   "large"   "small"   "large"   "small"  
[23] "UNKNOWN"
# here integer 0L is needed instead of real 0.0 
# manyNumbersWithNA contains integer numbers and the method complains
if_else( manyNumbersWithNA >= 500, manyNumbersWithNA, 0L ) 
 [1] 840   0  NA 756   0 502 507   0 534 860 842   0 625 751 532  NA 528 633 531   0 692   0  NA

Duplicates and unique elements

unique( duplicatedNumbers )
[1] 1 3 4 2
unique( c( NA, duplicatedNumbers, NA ) )
[1] NA  1  3  4  2
duplicated( duplicatedNumbers )
 [1] FALSE FALSE  TRUE FALSE FALSE  TRUE  TRUE  TRUE  TRUE  TRUE

Positions of max/min elements

which.max( manyNumbersWithNA )
[1] 10
manyNumbersWithNA[ which.max( manyNumbersWithNA ) ]
[1] 860
which.min( manyNumbersWithNA )
[1] 8
manyNumbersWithNA[ which.min( manyNumbersWithNA ) ]
[1] 76
range( manyNumbersWithNA, na.rm = TRUE )
[1]  76 860

Sorting/ordering of vectors

manyNumbersWithNA
 [1] 840  80  NA 756 277 502 507  76 534 860 842 196 625 751 532  NA 528 633 531 496 692 474  NA
sort( manyNumbersWithNA )
 [1]  76  80 196 277 474 496 502 507 528 531 532 534 625 633 692 751 756 840 842 860
sort( manyNumbersWithNA, na.last = TRUE )
 [1]  76  80 196 277 474 496 502 507 528 531 532 534 625 633 692 751 756 840 842 860  NA  NA  NA
sort( manyNumbersWithNA, na.last = TRUE, decreasing = TRUE )
 [1] 860 842 840 756 751 692 633 625 534 532 531 528 507 502 496 474 277 196  80  76  NA  NA  NA
manyNumbersWithNA[1:5]
[1] 840  80  NA 756 277
order( manyNumbersWithNA[1:5] )
[1] 2 5 4 1 3
rank( manyNumbersWithNA[1:5] )
[1] 4 1 5 3 2
sort( mixedLetters )
 [1] "a" "e" "H" "J" "k" "n" "s" "T" "Y" "Z"

Ranking of vectors

manyDuplicates <- sample( 10:15, 10, replace = TRUE )
rank( manyDuplicates )
 [1] 8.5 8.5 2.5 6.0 5.0 2.5 2.5 2.5 8.5 8.5
rank( manyDuplicates, ties.method = "min" )
 [1] 7 7 1 6 5 1 1 1 7 7
rank( manyDuplicates, ties.method = "random" )
 [1]  8  9  4  6  5  3  1  2 10  7

Rounding numbers

v <- c( -1, -0.5, 0, 0.5, 1, rnorm( 10 ) )
v
 [1] -1.0000000 -0.5000000  0.0000000  0.5000000  1.0000000 -1.7573167  0.4183369  0.1402900  1.4431644 -1.7079912
[11]  1.2588231  0.2619085  0.2643704  1.9361729  0.3206620
round( v, 0 )
 [1] -1  0  0  0  1 -2  0  0  1 -2  1  0  0  2  0
round( v, 1 )
 [1] -1.0 -0.5  0.0  0.5  1.0 -1.8  0.4  0.1  1.4 -1.7  1.3  0.3  0.3  1.9  0.3
round( v, 2 )
 [1] -1.00 -0.50  0.00  0.50  1.00 -1.76  0.42  0.14  1.44 -1.71  1.26  0.26  0.26  1.94  0.32
floor( v )
 [1] -1 -1  0  0  1 -2  0  0  1 -2  1  0  0  1  0
ceiling( v )
 [1] -1  0  0  1  1 -1  1  1  2 -1  2  1  1  2  1

Naming vector elements

heights <- c( Amy = 166, Eve = 170, Bob = 177 )
heights
Amy Eve Bob 
166 170 177 
names( heights )
[1] "Amy" "Eve" "Bob"
names( heights ) <- c( "AMY", "EVE", "BOB" )
heights
AMY EVE BOB 
166 170 177 
heights[[ "EVE" ]]
[1] 170

Generating grids

expand_grid( x = c( 1:3, NA ), y = c( "a", "b" ) )
# A tibble: 8 × 2
      x y    
  <int> <chr>
1     1 a    
2     1 b    
3     2 a    
4     2 b    
5     3 a    
6     3 b    
7    NA a    
8    NA b    

Generating combinations

combn( c( "a", "b", "c", "d", "e" ), m = 2, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  "c"  "d"  
[2,] "b"  "c"  "d"  "e"  "c"  "d"  "e"  "d"  "e"  "e"  
combn( c( "a", "b", "c", "d", "e" ), m = 3, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  
[2,] "b"  "b"  "b"  "c"  "c"  "d"  "c"  "c"  "d"  "d"  
[3,] "c"  "d"  "e"  "d"  "e"  "e"  "d"  "e"  "e"  "e"  


Copyright © 2022 Biomedical Data Sciences (BDS) | LUMC